# Intelligent agent

Steel MCP Server is a Model Context Protocol (MCP) server based on Puppeteer and Steel, enabling LLMs such as Claude to perform web page navigation and interaction through browser automation tools.

An intelligent task management system based on the MCP protocol, providing an efficient programming workflow framework for AI agents, with functions such as task planning, decomposition, execution, and memory.

This project demonstrates how to use the MCP protocol to connect multiple servers with different transport methods (stdio and SSE), including mathematical calculation and weather query functions, and integrates with LangChain to create intelligent agents.

This project creates or utilizes multiple MCP servers to integrate with the intelligent agent framework and Microsoft Copilot Studio.

A simple agent program that uses the OpenAI Agents library to interact with the MCP server, supporting functions such as calculating the sum of numbers or telling jokes.

A client project based on Python 3.13 that integrates MCP services and the GPT-4 model, providing interactive tool invocation and network search functionality.

Pixelle MCP is an omnimodal AIGC solution based on the MCP protocol, which can convert ComfyUI workflows into MCP tools without code, achieving seamless integration between LLM and ComfyUI.

An MCP server developed in TypeScript that serves as an intelligent bridge between natural language requests and Azure CLI execution, providing planning/execution processes, security protection, audit tracking, and adaptation to multiple Azure services.

RAG project based on MCP server

Intelligent agent system integrating custom MCP protocol and ChatGPT AI template, supporting Gmail and GitHub interaction

The Agentic MCP server is an extension of the standard MCP server, with autonomous decision-making, state management, and dynamic interaction capabilities, supporting complex workflows and intelligent data processing.

This project demonstrates how to combine LlamaIndex with MCP tool integration to build an intelligent agent capable of real-time weather information query through the OpenWeather API.

An intelligent agent system for detecting code errors

An AI software architect server based on the MCP protocol that can analyze codebases to generate product requirement documents (PRDs) and provide reasoning assistance for complex coding tasks. It uses a multi-model architecture and intelligent agent design.

DigitalFate is an enterprise-level framework for efficiently coordinating LLM calls, intelligent agents, and computer tasks, providing scalable production environment deployment, task-oriented architecture, and multi-client processing capabilities.

This project demonstrates how to combine the local Ollama model with the Pydantic proxy framework to create intelligent agents and use tools through the MCP server, while providing a Streamlit user interface.

A configurable MCP server SSH client with an intelligent security agent function that can detect and block the execution of unsafe commands in SSH connections.

Claude code editing and execution service implemented based on the MCP protocol

BuildAutomata Memory is a persistent memory system based on the MCP protocol, providing semantic search and versioned memory storage across sessions for AI agents, supporting intelligent classification, timeline tracing, and multi-tool synchronization